SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2208.08307 · 2022

SC-Explorer: Incremental 3D Scene Completion for Safe and Efficient Exploration Mapping and Planning

arXiv · PDF · Open in the Atlas

Code that ran

6 of 7 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 5 have no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2208.08307.json · badge: /api/ran/2208.08307.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ethz-asl/ssc_exploration canonical (classifier label)
classifier basis not recorded on the link
6 ran · 1 no recorded run
FunctionStatusWhere it lives
create_figure_object Ran
ran on a synthesized input
ethz-asl/ssc_exploration/ssc_mapping/src/eval/eval_plots.py
code served (permissive licence) · get_code("755435b4c545f3e3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import matplotlib.pyplot as plt
import math

ARGS = {
    "num_plots": 5,
    "width": 16,
    "height": 10,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
downsample_voxel Ran
ran on a synthesized input
ethz-asl/ssc_exploration/ssc_network/utils/utils.py
code served (permissive licence) · get_code("bdc26789c318a84f")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 3, dtype family int, shape (60, 36, 60) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a small labeled voxel array with shape (240, 144, 240)
# Fill it with a mix of 0, 255, and some intermediate values (1-254)
label = np.zeros((240, 144, 240), dtype=np.uint8)

# Add some non-empty regions with various label values
label[0:80, 0:48, 0:80] = 1  # Region with label 1
label[80:160, 48:96, 80:160] = 2  # Region with label 2
label[160:240, 96:144, 160:240] = 255  # Region with label 255

# Add some scattered values in between
label[40:120, 24:72, 40:120] = 3

ARGS = {
    "label": label,
    "voxel_size": (240, 144, 240),
    "downscale": 4
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 3, dtype family int, shape (60, 36, 60) — shape (60, 36, 60) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_iou Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ethz-asl/ssc_exploration/ssc_network/utils/ssc_metrics.py
code served (permissive licence) · get_code("251f4945130ffbc3")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Analyzing the function:
# - iou_sum: numpy array, shape[0] accessed, indexed by idx, used in division
# - cnt_class: numpy array, same shape as iou_sum, indexed by idx, used in division and slicing [1:]
# The function computes IoU per class and mean IoU across classes (excluding class 0)

# Create small numpy arrays with distinct sizes
# _C (number of classes) = 4
num_classes = 4

# iou_sum: accumulated intersection over union values per class
iou_sum = np.array([100.0, 50.0, 75.0, 25.0], dtype=np.float32)

# cnt_class: count of samples per class (must be non-zero for classes 1-3 to compute mean_iou)
cnt_class = np.array([10, 5, 6, 5], dtype=np.float32)

ARGS = {
    "iou_sum": iou_sum,
    "cnt_class": cnt_class,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_occupancy_calibration Ran
ran on a synthesized input
ethz-asl/ssc_exploration/ssc_network/utils/ssc_metrics.py
code served (permissive licence) · get_code("47581367af72e4de")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 2, dtype family int; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Construct valid arguments for get_occupancy_calibration
# The function expects:
# - predict: shape (batch_size, num_classes, spatial_dims...) with logits/scores
# - target: shape (batch_size, spatial_dims...) with class labels

batch_size = 2
num_classes = 4
spatial_size = 3

# Create predict array: (batch_size, num_classes, spatial_size)
# Contains logit-like values that will be argmaxed along axis 1
predict = np.random.randn(batch_size, num_classes, spatial_size).astype(np.float32)

# Create target array: (batch_size, spatial_size) with class labels
# Values should be in range [0, num_classes) mostly, with a few values > num_classes to test the warning
target = np.array([
    [0, 1, 2],
    [1, 3, 0]
], dtype=np.int32)

ARGS = {
    "predict": predict,
    "target": target
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, dtype family int — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_origin_from_depth_image Ran
ran on a synthesized input
ethz-asl/ssc_exploration/ssc_network/utils/utils.py
code served (permissive licence) · get_code("04c99b81989032f4")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 1, dtype family float, shape (3,) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a small depth image (H=2, W=3)
depth = np.array([
    [1.0, 1.5, 2.0],
    [1.2, 1.8, 2.2]
], dtype=np.float32)

# Camera intrinsic matrix (3x3, but only using [0][0], [0][2], [1][1], [1][2])
cam_k = np.array([
    [500.0, 0.0, 160.0],    # fx, 0, cx
    [0.0, 500.0, 120.0],    # 0, fy, cy
    [0.0, 0.0, 1.0]
], dtype=np.float32)

# Camera pose: 4x4 transformation matrix (rotation + translation)
# Using identity rotation with small translation
cam_pose = np.array([
    [1.0, 0.0, 0.0, 0.5],
    [0.0, 1.0, 0.0, 0.3],
    [0.0, 0.0, 1.0, 0.1],
    [0.0, 0.0, 0.0, 1.0]
], dtype=np.float32)

ARGS = {
    "depth": depth,
    "cam_k": cam_k,
    "cam_pose": cam_pose
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (3,) — shape (3,) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
read_plot_data_csv Ran
ran on a synthesized input
ethz-asl/ssc_exploration/ssc_mapping/src/eval/eval_plots.py
code served (permissive licence) · get_code("5b1ad9405e2c9725")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import csv
import tempfile
import os

# Create a temporary CSV file with sample data
temp_dir = tempfile.mkdtemp()
csv_file_path = os.path.join(temp_dir, "test_data.csv")

# Write sample CSV data
with open(csv_file_path, 'w', newline='\n') as f:
    writer = csv.writer(f, delimiter=',')
    writer.writerow(['x', 'y', 'z'])
    writer.writerow(['1.0', '2.5', '3.7'])
    writer.writerow(['4.2', '5.1', '6.9'])
    writer.writerow(['7.3', '8.4', '9.2'])

ARGS = {
    'csv_file': csv_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_accuracy Not yet run
unverified (harvested, no recorded run)
ethz-asl/ssc_exploration/ssc_network/utils/ssc_metrics.py
code served (permissive licence) · get_code("40d8d0dfd5686afe")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 2 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
get_accuracy 5 other papers
1 dated earlier, 4 later
2112.00726 (2021-12)
MonoScene: Monocular 3D Semantic Scene Completion
2302.13540 (2023-02)
OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion
2305.16133 (2023-05)
OVO: Open-Vocabulary Occupancy
and 2 more not named here
get_iou 5 other papers
1 dated earlier, 4 later
2112.00726 (2021-12)
MonoScene: Monocular 3D Semantic Scene Completion
2302.13540 (2023-02)
OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion
2305.16133 (2023-05)
OVO: Open-Vocabulary Occupancy
and 2 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Exploration of unknown environments is a fundamental problem in robotics and an essential component in numerous applications of autonomous systems. A major challenge in exploring unknown environments is that the robot has to plan with the limited information available at each time step. While most current approaches rely on heuristics and assumption to plan paths based on these partial observations, we instead propose a novel way to integrate deep learning into exploration by leveraging 3D scene completion for informed, safe, and interpretable exploration mapping and planning. Our approach, SC-Explorer, combines scene completion using a novel incremental fusion mechanism and a newly proposed hierarchical multi-layer mapping approach, to guarantee safety and efficiency of the robot. We further present an informative path planning method, leveraging the capabilities of our mapping approach and a novel scene-completion-aware information gain. While our method is generally applicable, we evaluate it in the use case of a Micro Aerial Vehicle (MAV). We thoroughly study each component in high-fidelity simulation experiments using only mobile hardware, and show that our method can speed up coverage of an environment by 73% compared to the baselines with only minimal reduction in map accuracy. Even if scene completions are not included in the final map, we show that they can be used to guide the robot to choose more informative paths, speeding up the measurement of the scene with the robot's sensors by 35%. We validate our system on a fully autonomous MAV, showing rapid and reliable scene coverage even in a complex cluttered environment. We make our methods available as open-source.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2208.08307")
get_code_for_paper("2208.08307")
have("2208.08307")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2208.08307.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2208.08307.svg)](https://syntology.ai/paper/2208.08307)

Connect an agent — have() is free.